39 citations · 88 across the 8 of their papers we have counts for
3 papers · 1 filter
Can Transformers Learn to Solve Problems Recursively?
Shizhuo Dylan Zhang, Curt Tigges, Stella Biderman +2
Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in t…
Getting More out of Large Language Models for Proofs
Shizhuo Dylan Zhang, Talia Ringer, Emily First
Large language models have the potential to simplify formal theorem proving and make it more accessible. But how to get the most out of these models is still an open question. To a…
Large Language Models are Edge-Case Fuzzers: Testing Deep Learning Libraries via FuzzGPT
Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang +3
Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challengin…